Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    specific names or terms related to current events or political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or events within a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    surprisingly
    -0.52
     aback
    -0.50
    ensibly
    -0.50
    prisingly
    -0.49
     partName
    -0.49
    inarily
    -0.47
     surprised
    -0.47
     cautiously
    -0.47
     spokeswoman
    -0.47
     surveyed
    -0.46
    POSITIVE LOGITS
    )."
    0.88
    .'"
    0.81
    .).
    0.81
    )).
    0.81
    .''.
    0.80
    .�
    0.79
    .ãĢį
    0.76
    !".
    0.76
    '."
    0.75
    ."[
    0.74
    Act Density 1.480%

    No Known Activations